Re: [PATCH v8 5/7] spapr: move FORM1 verifications to post CAS

[Greg Kurz <groug@kaod.org>]

On Fri, 17 Sep 2021 18:28:00 -0300
Daniel Henrique Barboza <danielhb413@gmail.com> wrote:

> FORM2 NUMA affinity is prepared to deal with empty (memory/cpu less)
> NUMA nodes. This is used by the DAX KMEM driver to locate a PAPR SCM
> device that has a different latency than the original NUMA node from the
> regular memory. FORM2 is also able  to deal with asymmetric NUMA
> distances gracefully, something that our FORM1 implementation doesn't
> do.
> 
> Move these FORM1 verifications to a new function and wait until after
> CAS, when we're sure that we're sticking with FORM1, to enforce them.
> 
> Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
> ---

Reviewed-by: Greg Kurz <groug@kaod.org>

>  hw/ppc/spapr.c              | 33 -----------------------
>  hw/ppc/spapr_hcall.c        |  6 +++++
>  hw/ppc/spapr_numa.c         | 53 ++++++++++++++++++++++++++++++++-----
>  include/hw/ppc/spapr_numa.h |  1 +
>  4 files changed, 54 insertions(+), 39 deletions(-)
> 
> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> index d39fd4e644..ada85ee083 100644
> --- a/hw/ppc/spapr.c
> +++ b/hw/ppc/spapr.c
> @@ -2773,39 +2773,6 @@ static void spapr_machine_init(MachineState *machine)
>      /* init CPUs */
>      spapr_init_cpus(spapr);
>  
> -    /*
> -     * check we don't have a memory-less/cpu-less NUMA node
> -     * Firmware relies on the existing memory/cpu topology to provide the
> -     * NUMA topology to the kernel.
> -     * And the linux kernel needs to know the NUMA topology at start
> -     * to be able to hotplug CPUs later.
> -     */
> -    if (machine->numa_state->num_nodes) {
> -        for (i = 0; i < machine->numa_state->num_nodes; ++i) {
> -            /* check for memory-less node */
> -            if (machine->numa_state->nodes[i].node_mem == 0) {
> -                CPUState *cs;
> -                int found = 0;
> -                /* check for cpu-less node */
> -                CPU_FOREACH(cs) {
> -                    PowerPCCPU *cpu = POWERPC_CPU(cs);
> -                    if (cpu->node_id == i) {
> -                        found = 1;
> -                        break;
> -                    }
> -                }
> -                /* memory-less and cpu-less node */
> -                if (!found) {
> -                    error_report(
> -                       "Memory-less/cpu-less nodes are not supported (node %d)",
> -                                 i);
> -                    exit(1);
> -                }
> -            }
> -        }
> -
> -    }
> -
>      spapr->gpu_numa_id = spapr_numa_initial_nvgpu_numa_id(machine);
>  
>      /* Init numa_assoc_array */
> diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
> index 9056644890..222c1b6bbd 100644
> --- a/hw/ppc/spapr_hcall.c
> +++ b/hw/ppc/spapr_hcall.c
> @@ -1198,6 +1198,12 @@ target_ulong do_client_architecture_support(PowerPCCPU *cpu,
>      spapr->cas_pre_isa3_guest = !spapr_ovec_test(ov1_guest, OV1_PPC_3_00);
>      spapr_ovec_cleanup(ov1_guest);
>  
> +    /*
> +     * Check for NUMA affinity conditions now that we know which NUMA
> +     * affinity the guest will use.
> +     */
> +    spapr_numa_associativity_check(spapr);
> +
>      /*
>       * Ensure the guest asks for an interrupt mode we support;
>       * otherwise terminate the boot.
> diff --git a/hw/ppc/spapr_numa.c b/hw/ppc/spapr_numa.c
> index 7339d00d20..dfe4fada01 100644
> --- a/hw/ppc/spapr_numa.c
> +++ b/hw/ppc/spapr_numa.c
> @@ -193,6 +193,48 @@ static void spapr_numa_define_FORM1_domains(SpaprMachineState *spapr)
>  
>  }
>  
> +static void spapr_numa_FORM1_affinity_check(MachineState *machine)
> +{
> +    int i;
> +
> +    /*
> +     * Check we don't have a memory-less/cpu-less NUMA node
> +     * Firmware relies on the existing memory/cpu topology to provide the
> +     * NUMA topology to the kernel.
> +     * And the linux kernel needs to know the NUMA topology at start
> +     * to be able to hotplug CPUs later.
> +     */
> +    if (machine->numa_state->num_nodes) {
> +        for (i = 0; i < machine->numa_state->num_nodes; ++i) {
> +            /* check for memory-less node */
> +            if (machine->numa_state->nodes[i].node_mem == 0) {
> +                CPUState *cs;
> +                int found = 0;
> +                /* check for cpu-less node */
> +                CPU_FOREACH(cs) {
> +                    PowerPCCPU *cpu = POWERPC_CPU(cs);
> +                    if (cpu->node_id == i) {
> +                        found = 1;
> +                        break;
> +                    }
> +                }
> +                /* memory-less and cpu-less node */
> +                if (!found) {
> +                    error_report(
> +"Memory-less/cpu-less nodes are not supported with FORM1 NUMA (node %d)", i);
> +                    exit(EXIT_FAILURE);
> +                }
> +            }
> +        }
> +    }
> +
> +    if (!spapr_numa_is_symmetrical(machine)) {
> +        error_report(
> +"Asymmetrical NUMA topologies aren't supported in the pSeries machine using FORM1 NUMA");
> +        exit(EXIT_FAILURE);
> +    }
> +}
> +
>  /*
>   * Set NUMA machine state data based on FORM1 affinity semantics.
>   */
> @@ -250,12 +292,6 @@ static void spapr_numa_FORM1_affinity_init(SpaprMachineState *spapr,
>          return;
>      }
>  
> -    if (!spapr_numa_is_symmetrical(machine)) {
> -        error_report("Asymmetrical NUMA topologies aren't supported "
> -                     "in the pSeries machine");
> -        exit(EXIT_FAILURE);
> -    }
> -
>      spapr_numa_define_FORM1_domains(spapr);
>  }
>  
> @@ -265,6 +301,11 @@ void spapr_numa_associativity_init(SpaprMachineState *spapr,
>      spapr_numa_FORM1_affinity_init(spapr, machine);
>  }
>  
> +void spapr_numa_associativity_check(SpaprMachineState *spapr)
> +{
> +    spapr_numa_FORM1_affinity_check(MACHINE(spapr));
> +}
> +
>  void spapr_numa_write_associativity_dt(SpaprMachineState *spapr, void *fdt,
>                                         int offset, int nodeid)
>  {
> diff --git a/include/hw/ppc/spapr_numa.h b/include/hw/ppc/spapr_numa.h
> index 6f9f02d3de..7cb3367400 100644
> --- a/include/hw/ppc/spapr_numa.h
> +++ b/include/hw/ppc/spapr_numa.h
> @@ -24,6 +24,7 @@
>   */
>  void spapr_numa_associativity_init(SpaprMachineState *spapr,
>                                     MachineState *machine);
> +void spapr_numa_associativity_check(SpaprMachineState *spapr);
>  void spapr_numa_write_rtas_dt(SpaprMachineState *spapr, void *fdt, int rtas);
>  void spapr_numa_write_associativity_dt(SpaprMachineState *spapr, void *fdt,
>                                         int offset, int nodeid);